Statements (30)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:multimodal_AI_model
|
| gptkbp:architecture |
two-stream model
|
| gptkbp:author |
gptkb:Devi_Parikh
gptkb:Dhruv_Batra Jiasen Lu Stefan Lee |
| gptkbp:basedOn |
gptkb:BERT
|
| gptkbp:developedBy |
gptkb:Facebook_AI_Research
|
| gptkbp:enables |
image captioning
visual question answering visual commonsense reasoning |
| gptkbp:handles |
vision and language tasks
|
| gptkbp:input |
gptkb:text
images |
| gptkbp:introducedIn |
2019
|
| gptkbp:notablePublication |
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
|
| gptkbp:publishedIn |
gptkb:NeurIPS_2019
|
| gptkbp:relatedTo |
gptkb:UNITER
gptkb:LXMERT VisualBERT |
| gptkbp:repository |
https://github.com/facebookresearch/vilbert-multi-task
|
| gptkbp:trainer |
gptkb:COCO
gptkb:Visual_Genome gptkb:Conceptual_Captions |
| gptkbp:uses |
gptkb:transformation
|
| gptkbp:bfsParent |
gptkb:UNITER
gptkb:Multimodal_Bitransformers gptkb:Visual_Question_Answering |
| gptkbp:bfsLayer |
8
|
| https://www.w3.org/2000/01/rdf-schema#label |
ViLBERT
|